Fast approximate nearest neighbor searching in Rust, based on HNSW index
Go to file
Dirkjan Ochtman de38b64358 Lower Layer impls to slice impls to fix clippy suggestion 2021-01-20 22:05:22 +01:00
.github/workflows Add CI configuration 2020-12-16 10:17:29 +01:00
benches Lower Layer impls to slice impls to fix clippy suggestion 2021-01-20 22:05:22 +01:00
src Lower Layer impls to slice impls to fix clippy suggestion 2021-01-20 22:05:22 +01:00
tests Remove unused import 2021-01-19 11:14:34 +01:00
.gitignore Add simple benchmark 2021-01-20 13:25:06 +01:00
Cargo.toml Use specialized set implementation for faster tracking of visited points 2021-01-20 15:04:30 +01:00
README.md Add an inital README 2020-12-16 10:30:45 +01:00
cover.svg Add an inital README 2020-12-16 10:30:45 +01:00
deny.toml Add configuration for cargo-deny 2020-12-16 10:17:29 +01:00

README.md

Cover logo

Instant Distance: fast HNSW indexing

Build status License: MIT License: Apache 2.0

Instance Distance is a fast pure-Rust implementation of the Hierarchical Navigable Small Worlds paper by Malkov and Yashunin for finding approximate nearest neighbors. This implementation will power the InstantDomainSearch.com backend services used for word vector indexing.